Amazon robot competition won by shelf stacking AI that could one day be used in warehouses

The Amazon robotic Picking Challenge is a now annual competition that searches for robots that could one day work in the company's vast warehouses and its second champion has been announced. This year's winner was a joint effort, created by TU Delft Robotics Institute from the Netherlands and the company Delft Robotics. The team's robotic arm used a combination of a suction cup, a gripper, a depth-sensing camera, and deep learning artificial intelligence to pick and stow items from a mock Amazon warehouse shelf with greater speed and accuracy than the 15 other entries in the competition. TU Delft's creation's greatest asset was its adaptive deep learning which allowed it to scan the different shapes and sizes of the objects it was picking up and adjust how it manipulated them accordingly. The robot was able to pick items from the shelf with a speed of over 100 items per hour which is an impressive three times faster than last year's winner, even though Amazon had made the challenges much tougher "with denser bins, occluded items, and products that are more difficult to see and grasp."